Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
Whisper large - Noc Operation
This model is a fine-tuned version of biodatlab/whisper-th-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2294
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 3500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3633 | 0.6024 | 700 | 0.2652 |
| 0.3247 | 1.2048 | 1400 | 0.2417 |
| 0.3096 | 1.8072 | 2100 | 0.2334 |
| 0.304 | 2.4096 | 2800 | 0.2304 |
| 0.3065 | 3.0120 | 3500 | 0.2294 |
Framework versions
- PEFT 0.17.1
- Transformers 4.48.0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.4
- Downloads last month
- 10
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Mahafit/noc_combine_lora_1500step_v3
Base model
biodatlab/whisper-th-large-v3